基于红外图像的笼养白羽肉鸡体温检测方法  

Temperature detection method of caged white feather broilers based on infrared image

作　　者：姜来 王英超 霍晓静[1,2] 王辉 王文娣[1,2] 唐娟 李丽华[1,2] JIANG Lai;WANG Yingchao;HUO Xiaojing;WANG Hui;WANG Wendi;TANG Juan;LI Lihua(College of Mechanical and Electrical Engineering,Hebei Agricultural University,Baoding 071001,China;Key Laboratory of Broiler and Layer Breeding Facilities Engineering,Ministry of Agriculture and Rural Affairs/Hebei Provincial Key Laboratory of Intelligent Equipment and New Energy Utilization of Livestock and Poultry Breeding,Baoding 071001,China)

机构地区：[1]河北农业大学机电工程学院,河北保定071001 [2]农业农村部肉蛋鸡养殖设施工程重点实验室/河北省畜禽养殖智能装备与新能源利用重点实验室,河北保定071001

出　　处：《华南农业大学学报》2024年第2期304-310,共7页Journal of South China Agricultural University

基　　金：国家自然科学基金(31902209);河北省重点研发计划(20327220D);河北省现代农业产业技术体系创新团队建设项目(HBCT2018060204)。

摘　　要：【目的】针对大规模笼养肉鸡体温自动检测困难的问题,提出一种深度学习与回归分析相结合的肉鸡体温检测方法。【方法】采用红外热成像仪采集肉鸡的红外图像,通过YOLOv5s深度学习算法训练感兴趣区域(肉鸡鸡头)模型,分别引入多元线性回归和多元非线性回归以建立肉鸡感兴趣区域温度与翅下温度的预测模型,从而实现自动体温检测。【结果】基于深度学习的感兴趣区域模型的精准率与召回率分别为93.8%和95.8%,多元线性回归温度预测模型1和多元非线性回归温度预测模型的平均相对误差分别为0.28%和0.27%,温度预测值与真实值的最大差值分别为0.34和0.32℃。【结论】非线性模型预测肉鸡体温的准确率更高,可为日后舍内鸡只温度自动巡检设备提供技术支撑及前期研究基础。【Objective】To address the challenge of automatic temperature detection for large-scale caged broilers,a method combining deep learning and regression analysis was proposed.【Method】An infrared thermal imager was used to capture infrared images of broiler chickens,the YOLOv5s deep learning algorithm was used to train the model for the region of interest(broiler chicken head).Multiple linear regression and multiple nonlinear regression were respectively introduced to establish prediction models between the temperature of the broiler’s region of interest and the temperature under its wings,ultimately achieving the goal of automatic body temperature detection.【Result】The test results showed that the precision and recall of the region of interest model based on deep learning were 93.8%and 95.8%respectively.The average relative errors of the multiple linear regression 1 and multiple nonlinear regression temperature prediction models were 0.28%and 0.27%respectively,and the maximum differences between the predicted and actual temperature values were 0.34 and 0.32℃respectively.【Conclusion】The nonlinear model has a higher accuracy rate in predicting the body temperature of broilers,providing technical support and a preliminary research basis for automated in-house temperature inspection equipment for chicken farming.

关 键 词：深度学习 红外热成像 温度检测 肉鸡 反演 

分 类 号：S831.4[农业科学—畜牧学] TP23[农业科学—畜牧兽医]